grep -r "Code" /news · home›search
grep -rli "Code" /news

Code

Full-text search across 71060 articles. Combine with topic and date filters; results sorted by relevance.

results 71060 page 1593/3553 follow RSS for this search
00:00
2026-08-04
conductor.build
ai-tools

Conductor 0.79.0: Cloud Polish #1

Conductor 0.79.0, a cloud-focused update to the AI coding agent, introduces simplified onboarding, Vercel AI Gateway API key support, and an experimental Pierre editor for direct file editing in diffs, alongside fixes fo…

07:53
2026-08-03
snipvote.com
generative-ai

14 models tested on SVG frog prompt, all 42 runs produced output

A community test of 14 AI models on an SVG frog prompt found that all 42 runs produced output, according to a Hacker News post. The test, hosted at frogs.vaguespac.es, evaluated the models' ability to generate SVG code f…

05:47
2026-08-02
dev.to
developer-tools

Day 23/30: Expose Tools with MCP

A developer detailed the process of building an MCP server to expose tools to AI applications, using a sentiment analysis tool as an example. The team's support bot, powered by LangGraph and MCP, initially struggled with…

05:20
2026-08-02
dev.to
artificial-intelligence

I Let an AI Write My Tests for 30 Days: Coverage Went 38% to 71%

A developer reports that using an open-source AI agent called 'the-agent' to generate and maintain tests for 30 days increased code coverage from 38% to 71% without writing a single test by hand. The developer integrated…

23:07
2026-07-31
gist.github.com
developer-tools

Sick of AI agents thinking they're geniuses.

A developer created a bash script that blocks AI agents from using Homebrew on a system, displaying a warning message and exiting with code 42. The script instructs agents to use Nix instead, aiming to enforce system-spe…

20:57
2026-07-31
dev.to
machine-learning

Why INT4 Weight-Only Quantization Doesn't Speed Up Prefill

A developer's analysis shows that INT4 weight-only quantization speeds up decode but not prefill, because prefill is compute-bound while decode is memory-bound. The crossover point where a GEMM becomes compute-bound is l…

17:15
2026-07-31
machinebrief.com
artificial-intelligence

AI Software Development Metrics That Measure More Than Speed

Forbes Councils Expert Panel reports that CTOs need metrics beyond speed to evaluate AI's impact on software development, emphasizing quality, maintainability, and business outcomes. The panel suggests tracking defect ra…

16:07
2026-07-31
promptcube3.com
developer-tools

statvfs, /proc, and my first unsafe block in Rust

A developer recounts using an unsafe block in Rust to read /proc/self/mounts before discovering libc already provides the functionality. The post highlights a common learning curve in Rust systems programming, where unsa…

16:09
2026-07-30
gist.github.com
developer-tools

Config Qwen in OpenCode

A developer shared a configuration guide for integrating Qwen AI models into OpenCode on Ubuntu Linux, providing the JSON configuration file path and code snippet for setting up the Qwen provider with API tokens.

15:43
2026-07-30
simonwillison.net
ai-tools

llm-chat-completions-server 0.1a0

Simon Willison released llm-chat-completions-server 0.1a0, a plugin that exposes LLM models via an OpenAI Chat Completions-compatible endpoint. The plugin leverages content-addressable logs in LLM 0.32rc1 to de-duplicate…

03:22
2026-07-29
koreatimes.co.kr
artificial-intelligence

DDH builds trust in dental care with AI

DDH, a Korean dental AI startup, has developed Pano, an AI tool that analyzes panoramic X-rays and uses color coding to highlight potential dental issues, aiming to bridge the trust gap between patients and dentists. Fou…

22:01
2026-07-28
theregister.com
ai-safety

Looks like JFrog's 0-days let OpenAI's models hack Hugging Face

JFrog security researchers discovered that OpenAI's AI models could be tricked into exploiting zero-day vulnerabilities in Hugging Face's infrastructure, demonstrating a new class of AI-powered supply chain attacks. The …

02:37
2026-07-28
matthewsaltz.com
ai-tools

Using an open model feels surprisingly good

A user reports a surprisingly positive experience using the open-source coding tool opencode with a self-hosted inference endpoint, describing it as freeing and private. The user, who works at Modal, tested the newly lau…

17:44
2026-07-27
flyingpenguin.com
artificial-intelligence

Haversack of RAG: Demos AI Report Fails Its Own Disinformation Test

A Demos think tank paper claiming Russia rigged websites to make AI chatbots spread disinformation is undermined by its own evidence, as the technical signal it cites as proof of deliberate targeting appears in the think…

← prev page 1593 / 3553 next →